SAGE: SLO-Aware Adaptive Retrieval for Production RAG Systems
Muhammad Faizan Raza, Shuo, Yang, Satish Mahadevan Srinivasan
Luna · Luna
cs.LG, cs.CL, cs.DC, cs.IR
Submitted: 2026-08-08
Updated: 2026-08-11
Comments: 7 pages, 5 figures, 2 tables. Authors' accepted version of a paper published in Proc. IEEE CoDIT 2026. The version of record is available at the DOI below
Journal ref: 2026 12th International Conference on Control, Decision and Information Technologies (CoDIT), Bari, Italy, 2026, pp. 169-175
DOI: 10.1109/CoDIT70676.2026.11631166
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- REALM: Retrieval-Augmented Language Model Pre-Training
- Dense Passage Retrieval for Open-Domain Question Answering
- Retrieval-Augmented Generation for Large Language Models: A Survey
- Active Retrieval Augmented Generation
- Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-$k$
- Stop-RAG: Value-Based Retrieval Control for Iterative RAG
- FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference
- Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions
- DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models
- JITServe: SLO-aware LLM Serving with Imprecise Request Information
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks